Training in progress epoch 70

README.md

@@ -14,14 +14,14 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0520
-- Train Dice Coef: 0.8370
-- Train Iou: 0.7355
-- Validation Loss: 0.0446
-- Validation Dice Coef: 0.8852
-- Validation Iou: 0.7950
+- Train Loss: 0.0522
+- Train Dice Coef: 0.8487
+- Train Iou: 0.7473
+- Validation Loss: 0.0455
+- Validation Dice Coef: 0.8835
+- Validation Iou: 0.7923
 - Train Lr: 1e-10
-- Epoch: 69
+- Epoch: 70
 
 ## Model description
 
@@ -117,6 +117,7 @@ The following hyperparameters were used during training:
 | 0.0524     | 0.8461          | 0.7438    | 0.0452          | 0.8838               | 0.7928         | 1e-10    | 67    |
 | 0.0523     | 0.8374          | 0.7361    | 0.0453          | 0.8849               | 0.7947         | 1e-10    | 68    |
 | 0.0520     | 0.8370          | 0.7355    | 0.0446          | 0.8852               | 0.7950         | 1e-10    | 69    |
+| 0.0522     | 0.8487          | 0.7473    | 0.0455          | 0.8835               | 0.7923         | 1e-10    | 70    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e3303d120b2fd89636cd4742019c91b04bb00f486c7871701784ff23cadef9
+oid sha256:fddf5246180c653aca900d9aed19145b8f124559fec8ec206841e9d368cca5c2
 size 15133664